Merge branch 'main' into feat/session-data-masking

Author: sgmoorthy

.github/.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "1.29.0"
+  ".": "1.30.0"
 }

.github/release-please-config.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://raw.githubusercontent.com/googleapis/release-please/main/schemas/config.json",
-  "last-release-sha": "6b1600fbf53bcf634c5fe4793f02921bc0b75125",
+  "last-release-sha": "80a7ecf4b31e4c6de4a1425b03422f384c1a032d",
   "packages": {
     ".": {
       "release-type": "python",

CHANGELOG.md

@@ -1,5 +1,32 @@
 # Changelog
 
+## [1.30.0](https://github.com/google/adk-python/compare/v1.29.0...v1.30.0) (2026-04-13)
+
+
+### Features
+
+* Add Auth Provider support to agent registry ([f2c68eb](https://github.com/google/adk-python/commit/f2c68eb1536f1c0018c2cf7ee3f4417ca442080c))
+* Add Parameter Manager integration to ADK ([b0715d7](https://github.com/google/adk-python/commit/b0715d77a2a433bb2ed07a2475cc4d1f2d662b6c))
+* Add support for Gemma 4 models in ADK ([9d4ecbe](https://github.com/google/adk-python/commit/9d4ecbe9fd1141693e4682cbfe4d542cc62b76ac)), closes [#5156](https://github.com/google/adk-python/issues/5156)
+* allow users to include artifacts from artifact_service in A2A events using provided interceptor ([e63d991](https://github.com/google/adk-python/commit/e63d991be84e373fd31be29d4b6b0e32fdbde557))
+* emit a `TaskStatusUpdateEvent` for ADK events with no output parts but with event.actions ([dcc485b](https://github.com/google/adk-python/commit/dcc485b23e3509e2e386636d841033b91c9a401c))
+* Live avatar support in ADK ([a64a8e4](https://github.com/google/adk-python/commit/a64a8e46480753439b91b9cfd41fd190b4dad493))
+* **live:** expose live_session_resumption_update as Event in BaseLlmFlow ([2626ad7](https://github.com/google/adk-python/commit/2626ad7c69fb64a88372225d5583085fc08b1fcd)), closes [#4357](https://github.com/google/adk-python/issues/4357)
+* Promote BigQuery tools to Stable ([abcf14c](https://github.com/google/adk-python/commit/abcf14c166baf4f8cc6e919b1eb4c063bf3a92af))
+* **samples:** add sample for skill activation via environment tools ([2cbb523](https://github.com/google/adk-python/commit/2cbb52306910fac994fe1d29bdfcfacb258703b4))
+
+
+### Bug Fixes
+
+* Add "gcloud config unset project" command to express mode flow ([e7d8160](https://github.com/google/adk-python/commit/e7d81604126cbdb4d9ee4624e1d1410b06585750))
+* avoid load all agents in adk web server ([cb4dd42](https://github.com/google/adk-python/commit/cb4dd42eff2df6d20c5e53211718ecb023f127fc))
+* Change express mode user flow so it's more clear that an express mode project is being created ([0fedb3b](https://github.com/google/adk-python/commit/0fedb3b5eb2074999d8ccdb839e054ea80da486f))
+* Custom pickling in McpToolset to exclude unpicklable objects like errlog ([d62558c](https://github.com/google/adk-python/commit/d62558cc2d7d6c0372e43c9f009c8c7a6863ff0a))
+* Fix credential leakage vulnerability in Agent Registry ([e3567a6](https://github.com/google/adk-python/commit/e3567a65196bb453cdac4a5ae42f7f079476d748))
+* Include a link to the deployed agent ([547766a](https://github.com/google/adk-python/commit/547766a47779915a8a47745237a46882a02dae9a))
+* preserve interaction ids for interactions SSE tool calls ([9a19304](https://github.com/google/adk-python/commit/9a1930407a4eff67093ea9f14292f1931631a661)), closes [#5169](https://github.com/google/adk-python/issues/5169)
+* validate user_id and session_id against path traversal ([cbcb5e6](https://github.com/google/adk-python/commit/cbcb5e6002b5bae89de5309caf7b9bb02d563cfc)), closes [#5110](https://github.com/google/adk-python/issues/5110)
+
 ## [1.29.0](https://github.com/google/adk-python/compare/v1.28.0...v1.29.0) (2026-04-09)
 
 

contributing/samples/live_bidi_streaming_multi_agent/agent.py

@@ -30,11 +30,10 @@ def roll_die(sides: int) -> int:
 roll_agent = Agent(
     name="roll_agent",
     model=Gemini(
-        # see https://docs.cloud.google.com/vertex-ai/generative-ai/docs/migrate
-        # for vertex model names
-        model="gemini-live-2.5-flash-native-audio",  # vertex
-        # see https://ai.google.dev/gemini-api/docs/models for AIS model names
-        # model='gemini-2.5-flash-native-audio-latest',  # for AI studio
+        # Find supported models in Vertex here: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/live-api
+        model="gemini-live-2.5-flash-native-audio",  # Vertex
+        # Find supported models in Gemini API here: https://ai.google.dev/gemini-api/docs/models
+        # model='gemini-2.5-flash-native-audio-preview-12-2025',  # Gemini API
         speech_config=types.SpeechConfig(
             voice_config=types.VoiceConfig(
                 prebuilt_voice_config=types.PrebuiltVoiceConfig(
@@ -85,11 +84,10 @@ def check_prime(nums: list[int]) -> str:
 prime_agent = Agent(
     name="prime_agent",
     model=Gemini(
-        # see https://docs.cloud.google.com/vertex-ai/generative-ai/docs/migrate
-        # for vertex model names
-        model="gemini-live-2.5-flash-native-audio",  # vertex
-        # see https://ai.google.dev/gemini-api/docs/models for AIS model names
-        # model='gemini-2.5-flash-native-audio-latest',  # for AI studio
+        # Find supported models in Vertex here: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/live-api
+        model="gemini-live-2.5-flash-native-audio",  # Vertex
+        # Find supported models in Gemini API here: https://ai.google.dev/gemini-api/docs/models
+        # model='gemini-2.5-flash-native-audio-preview-12-2025',  # Gemini API
         speech_config=types.SpeechConfig(
             voice_config=types.VoiceConfig(
                 prebuilt_voice_config=types.PrebuiltVoiceConfig(
@@ -128,13 +126,11 @@ def get_current_weather(location: str):
 
 
 root_agent = Agent(
-    # find supported models here: https://google.github.io/adk-docs/get-started/streaming/quickstart-streaming/
     model=Gemini(
-        # see https://docs.cloud.google.com/vertex-ai/generative-ai/docs/migrate
-        # for vertex model names
-        model="gemini-live-2.5-flash-native-audio",  # vertex
-        # see https://ai.google.dev/gemini-api/docs/models for AIS model names
-        # model='gemini-2.5-flash-native-audio-latest',  # for AI studio
+        # Find supported models in Vertex here: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/live-api
+        model="gemini-live-2.5-flash-native-audio",  # Vertex
+        # Find supported models in Gemini API here: https://ai.google.dev/gemini-api/docs/models
+        # model='gemini-2.5-flash-native-audio-preview-12-2025',  # Gemini API
         speech_config=types.SpeechConfig(
             voice_config=types.VoiceConfig(
                 prebuilt_voice_config=types.PrebuiltVoiceConfig(

contributing/samples/live_bidi_streaming_parallel_tools_agent/agent.py

@@ -29,7 +29,10 @@ def turn_on_tv():
 
 
 root_agent = Agent(
-    model="gemini-live-2.5-flash-native-audio",
+    # Find supported models in Vertex here: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/live-api
+    model="gemini-live-2.5-flash-native-audio",  # Vertex
+    # Find supported models in Gemini API here: https://ai.google.dev/gemini-api/docs/models
+    # model='gemini-2.5-flash-native-audio-preview-12-2025',  # Gemini API
     name="Home_helper",
     instruction="Be polite and answer all user's questions.",
     tools=[turn_on_lights, turn_on_tv],

contributing/samples/live_bidi_streaming_single_agent/agent.py

@@ -65,11 +65,10 @@ async def check_prime(nums: list[int]) -> str:
 
 
 root_agent = Agent(
-    # see https://docs.cloud.google.com/vertex-ai/generative-ai/docs/migrate
-    # for vertex model names
-    model='gemini-live-2.5-flash-native-audio',  # vertex
-    # see https://ai.google.dev/gemini-api/docs/models for AIS model names
-    # model='gemini-2.5-flash-native-audio-latest',  # for AI studio
+    # Find supported models in Vertex here: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/live-api
+    model='gemini-live-2.5-flash-native-audio',  # Vertex
+    # Find supported models in Gemini API here: https://ai.google.dev/gemini-api/docs/models
+    # model='gemini-2.5-flash-native-audio-preview-12-2025',  # Gemini API
     name='roll_dice_agent',
     description=(
         'hello world agent that can roll a dice of 6 sides and check prime'

contributing/samples/live_bidi_streaming_tools_agent/agent.py

@@ -124,11 +124,10 @@ def stop_streaming(function_name: str):
 
 
 root_agent = Agent(
-    # see https://docs.cloud.google.com/vertex-ai/generative-ai/docs/migrate
-    # for vertex model names
-    model="gemini-live-2.5-flash-native-audio",  # vertex
-    # see https://ai.google.dev/gemini-api/docs/models for AIS model names
-    # model='gemini-2.5-flash-native-audio-latest',  # for AI studio
+    # Find supported models in Vertex here: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/live-api
+    model="gemini-live-2.5-flash-native-audio",  # Vertex
+    # Find supported models in Gemini API here: https://ai.google.dev/gemini-api/docs/models
+    # model='gemini-2.5-flash-native-audio-preview-12-2025',  # Gemini API
     name="video_streaming_agent",
     instruction="""
       You are a monitoring agent. You can do video monitoring and stock price monitoring

contributing/samples/live_tool_callbacks_agent/agent.py

@@ -217,9 +217,10 @@ async def after_tool_async_callback(
 
 # Create the agent with tool callbacks
 root_agent = Agent(
-    # find supported models here: https://google.github.io/adk-docs/get-started/streaming/quickstart-streaming/
-    model="gemini-2.0-flash-live-preview-04-09",  # for Vertex project
-    # model="gemini-live-2.5-flash-preview",  # for AI studio key
+    # Find supported models in Vertex here: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/live-api
+    model="gemini-live-2.5-flash-native-audio",  # Vertex
+    # Find supported models in Gemini API here: https://ai.google.dev/gemini-api/docs/models
+    # model='gemini-2.5-flash-native-audio-preview-12-2025',  # Gemini API
     name="tool_callbacks_agent",
     description=(
         "Live streaming agent that demonstrates tool callbacks functionality. "

pyproject.toml

@@ -44,11 +44,11 @@ dependencies = [
   "google-cloud-spanner>=3.56.0, <4.0.0",                    # For Spanner database
   "google-cloud-speech>=2.30.0, <3.0.0",                     # For Audio Transcription
   "google-cloud-storage>=2.18.0, <4.0.0",                    # For GCS Artifact service
-  "google-genai>=1.64.0, <2.0.0",                            # Google GenAI SDK
+  "google-genai>=1.72.0, <2.0.0",                            # Google GenAI SDK
   "graphviz>=0.20.2, <1.0.0",                                # Graphviz for graph rendering
   "httpx>=0.27.0, <1.0.0",                                   # HTTP client library
   "jsonschema>=4.23.0, <5.0.0",                              # Agent Builder config validation
-  "mcp>=1.23.0, <2.0.0",                                     # For MCP Toolset
+  "mcp>=1.24.0, <2.0.0",                                     # For MCP Toolset
   "opentelemetry-api>=1.36.0, <1.39.0",                      # OpenTelemetry - keep below 1.39.0 due to current agent_engines exporter constraints.
   "opentelemetry-exporter-gcp-logging>=1.9.0a0, <2.0.0",
   "opentelemetry-exporter-gcp-monitoring>=1.9.0a0, <2.0.0",
@@ -123,6 +123,7 @@ test = [
   "a2a-sdk>=0.3.0,<0.4.0",
   "anthropic>=0.43.0",                            # For anthropic model tests
   "crewai[tools];python_version>='3.11' and python_version<'3.12'",         # For CrewaiTool tests; chromadb/pypika fail on 3.12+
+  "google-cloud-firestore>=2.11.0, <3.0.0",
   "google-cloud-iamconnectorcredentials>=0.1.0, <0.2.0",
   "google-cloud-parametermanager>=0.4.0, <1.0.0",
   "kubernetes>=29.0.0",                           # For GkeCodeExecutor
@@ -159,6 +160,7 @@ extensions = [
   "beautifulsoup4>=3.2.2",                      # For load_web_page tool.
   "crewai[tools];python_version>='3.11' and python_version<'3.12'",       # For CrewaiTool; chromadb/pypika fail on 3.12+
   "docker>=7.0.0",                              # For ContainerCodeExecutor
+  "google-cloud-firestore>=2.11.0, <3.0.0",             # For Firestore services
   "google-cloud-parametermanager>=0.4.0, <1.0.0",
   "kubernetes>=29.0.0",                         # For GkeCodeExecutor
   "k8s-agent-sandbox>=0.1.1.post3",             # For GkeCodeExecutor sandbox mode

src/google/adk/agents/run_config.py

@@ -198,6 +198,9 @@ class RunConfig(BaseModel):
   response_modalities: Optional[list[str]] = None
   """The output modalities. If not set, it's default to AUDIO."""
 
+  avatar_config: Optional[types.AvatarConfig] = None
+  """Avatar configuration for the live agent."""
+
   save_input_blobs_as_artifacts: bool = Field(
       default=False,
       deprecated=True,